Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The new skill in AI is not prompting, it's context engineering

philschmid.de

Post reply on HN
Print view View original

361–370 of 550 posts

Re: The new skill in AI is not prompting, it's context engineering

#361

Post by belter »

mentalgear wrote: post #92
JohnMakin wrote: post #10

> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…

It's magical thinking all the way down. Whether they call it now "prompt" or "context" engineering because it's the same tinkering to find something that "sticks" in non-deterministic space.

Got it...updating CV to call myself a VibeOps Engineer in a team of Context Engineers...A few of us were let go last quarter, as they could only do Prompt Engineering.

Re: The new skill in AI is not prompting, it's context engineering

#362

Post by simonw »

xarope wrote: post #279
simonw wrote: post #46

Earlier quoted context omitted.

Drew isn't using that term in a military context, he's using it in a gaming context. He defines what he means very clearly: > The term “loadout” is a gaming term that refers to the specific combination of abilities, weapons, and equipment you select before a level, match, or round. In the military you don't select your abilities before entering a level.

the military definitely do use the term loadout. It can be based on mission parameters e.g. if armored vehicles are expected, your loadout might include more MANPATS. It can also refer to the way each soldier might customize their gear, e.g. cutaway knife in boot or on vest, NODs if extended night operations expected (I know, I know, gamers would like to think you'd bring everything, but in real life no warfighter wo…

Nobody is disputing that. We are saying that the statement "The term 'loudout' is a gaming term" can be true at the same time.

Re: The new skill in AI is not prompting, it's context engineering

#363

Post by niemandhier »

LLM agents remind me of the great Nolan movie „Memento“.

The agents cannot change their internal state hence they change the encompassing system.

They do this by injecting information into it in such a way that the reaction that is triggered in them compensates for their immutability.

For this reason I call my agents „Sammy Jenkins“.

Re: The new skill in AI is not prompting, it's context engineering

#364

Post by __loam »

skydhash wrote: post #354
felipeerias wrote: post #234

Earlier quoted context omitted.

If someone asked you about the usages of a particular element in a codebase, you would probably give a more accurate answer if you were able to use a code search tool rather than reading every source file from top to bottom. For that kind of tasks (and there are many of those!), I don't see why you would expect something fundamentally different in the case of LLMs.

But why not provide the search tool instead of being an imperfect interface between it and the person asking? The only reason for the latter is that you have more applied knowledge in the context and can use the tool better. For any other case, the answer should be “use this tool”.

The uninformed would rather have a natural language interface rather than learn how to actually use the tools.

Re: The new skill in AI is not prompting, it's context engineering

#365

Post by lblume »

v3ss0n wrote: post #334
JohnMakin wrote: post #10

> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…

At this point , due to non-deterministic nature and hallucination context engineering is pretty much magic. But here are our findings. 1 - LLM Tends to pick up and understand contexts that comes at top 7-12 lines.Mostly first 1k token is best understood by llms ( tested on Claude and several opensource models ) so - most important contexts like parsing rules need to be placed there. 2 - Need to keep context short . W…

I have uploaded entire books to the latest Gemini and had the model reliably accurately answer specific questions requiring knowledge of multiple chapters.

Re: The new skill in AI is not prompting, it's context engineering

#366

Post by slightwinder »

pbhjpbhj wrote: post #304
dawnofdusk wrote: post #269

Earlier quoted context omitted.

>This really does sound like Computer Science since it's very beginnings. Except in actual computer science you can prove that your strategies, discovered by trial and error, are actually good. Even though Dijkstra invented his eponymous algorithm by writing on a napkin, it's phrased in the language of mathematics and one can analyze quantitatively its effectiveness and trade-offs, and one can prove if it's optimal (…

Surely claims about context engineering can also be tested using scientific methodology?

Yes, in theory. But it's testing against highly complex, ever-changing systems, where small changes can have big impact on the outcome. So it's more akin to "weak" science like psychology. And weak here means that most finding have a weak standing, because of each variable having little individual contribution in the complex setup researched, making it harder to reproduce results.

Even more problematic is that too many "researchers" are just laymen, lacking a proper scientific background, and they are often just playing around with third-party-services, while delivering too much noise to the community.

So in general, AI has also something like the replication crisis in its own way. But on the other side, the latest wave of AI is just some years old (3 years now?), which is not much in real scientific progress-rates.

Re: The new skill in AI is not prompting, it's context engineering

#367

Post by thatthatis »

Glad we have a name for this. I had been calling it “context shaping” in my head for a bit now.

I think good context engineering will be one of the most important pieces of the tooling that will turn “raw model power” into incredible outcomes.

Model power is one thing, model power plus the tools to use it will be quite another.

Re: The new skill in AI is not prompting, it's context engineering

#368

Post by simonw »

colordrops wrote: post #293
JohnMakin wrote: post #10

> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…

> Since these are non-deterministic machines, I fail to see any reliable heuristic that is fundamentally indistinguishable than "trying and seeing" with prompts There are many sciences involving non-determinism that still have laws and patterns, e.g. biology and maybe psychology. It's not all or nothing. Also, LLMs are deterministic, just not predictable. The non-determinism is injected by providers. Anyway is there…

They arguably are two names for the same thing.

The difference is that "prompt engineering" as a term has failed, because to a lot of people the inferred definition is "a laughably pretentious term for typing text into a chatbot" - it's become indistinguishable from end-user prompting.

My hope is that "context engineering" better captures the subtle art of building applications on top of LLMs through carefully engineering their context.

Re: The new skill in AI is not prompting, it's context engineering

#369

Post by jedimastert »

ozgung wrote: post #319
0points wrote: post #313

Only more mental exercises to avoid reading the writing on the wall: LLM DO NOT REASON ! THEY ARE TOKEN PREDICTION MACHINES Thank you for your attention in this matter!

Why not? What is so special about reasoning that you cannot achieve by predicting tokens aka. constructing sentences?

Predicting tokens and constructing sentences are not the same thing. It cannot create its own sentences because it does not have a self

Re: The new skill in AI is not prompting, it's context engineering

#370

Post by simonw »

wiseowise wrote: post #350
ozgung wrote: post #333

Earlier quoted context omitted.

At least LLMs attempt to answer the question. You just avoided it without any reasoning.

Because LLMs do no reason. They reply without a thought. Parent commenter, on the other hand, knows when to not engage a bullshit argument. Arguing with “philosophers” like you is like arguing with religious nut jobs. Repeat after me: 1) LLM do not reason 2) Human thought is infinitely more complex than any LLM algorithm 3) If I ever try to confuse both, I go outside and touch some grass (and talk to actual humans)

I agree with your point 2. I can't decide if I agree with your point 1 unless you can explain what "reason" means.
Post reply on HN